Multi-class Cell Segmentation Using CNNs with F\(_1\)-measure Loss Function

  • Aaron Scherzinger
  • Philipp Hugenroth
  • Marike Rüder
  • Sven Bogdan
  • Xiaoyi JiangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11269)


Cell segmentation is one of the fundamental problems in biomedical image processing as it is often mandatory for the quantitative analysis of biological processes. Sometimes, a binary segmentation of the cells is not sufficient, for instance if biologists are interested in the appearance of specific cell parts. Such a setting requires multiple foreground classes, which can significantly increase the complexity of the segmentation task. This is especially the case if very fine structures need to be detected. Here, we propose a method for multi-class segmentation of Drosophila macrophages in in-vivo fluorescence microscopy images to segment complex cell structures such as the lamellipodium and filopodia. Our approach is based on a convolutional neural network, more specifically the U-net architecture. The network is trained using a loss function based on the F\(_1\)-measure which we have extended for multi-class scenarios to account for class imbalances in the image data. We compare the F\(_1\)-measure loss function to a weighted cross entropy loss and show that the CNN outperforms other segmentation approaches.


CNN F\(_1\)-measure Loss function Cell segmentation 


  1. 1.
    Akram, S.U., Kannala, J., Eklund, L., Heikkilä, J.: Cell proposal network for microscopy image analysis. In: IEEE International Conference on Image Processing (ICIP), pp. 3199–3203 (2016)Google Scholar
  2. 2.
    Akram, S.U., Kannala, J., Eklund, L., Heikkilä, J.: Cell segmentation proposal network for microscopy image analysis. In: Proceedings of Deep Learning and Data Labeling for Medical Applications, pp. 21–29 (2016)Google Scholar
  3. 3.
    Aydin, A.S., Dubey, A., Dovrat, D., Aharoni, A., Shilkrot, R.: CNN based yeast cell segmentation in multi-modal fluorescent microscopy data. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 753–759 (2017)Google Scholar
  4. 4.
    Barry, D.J., Durkin, C.H., Abella, J.V., Way, M.: Open source software for quantification of cell migration, protrusions, and fluorescence intensities. J. Cell Biol. 209(1), 163–180 (2015)CrossRefGoogle Scholar
  5. 5.
    Bergeest, J., Rohr, K.: Efficient globally optimal segmentation of cells in fluorescence microscopy images using level sets and convex energy functionals. Med. Image Anal. 16(7), 1436–1444 (2012)CrossRefGoogle Scholar
  6. 6.
    Bernier-Latmani, J., Petrova, T.V.: High-resolution 3D analysis of mouse small-intestinal stroma. Nat. Protoc. 119(9), 1617–1629 (2016)CrossRefGoogle Scholar
  7. 7.
    Bian, A., Scherzinger, A., Jiang, X.: An enhanced multi-label random walk for biomedical image segmentation using statistical seed generation. In: Proceedings of International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS), pp. 748–760 (2017)CrossRefGoogle Scholar
  8. 8.
    Bredies, K., Wolinski, H.: An active-contour based algorithm for the automated segmentation of dense yeast populations on transmission microscopy images. Comput. Vis. Sci. 14(7), 341–352 (2011)CrossRefGoogle Scholar
  9. 9.
    Castilla, C., Maska, M., Sorokin, D.V., Meijering, E., de Solorzano, C.O.: Segmentation of actin-stained 3D fluorescent cells with filopodial protrusions using convolutional neural networks. In: International Symposium on Biomedical Imaging (ISBI), pp. 413–417 (2018)Google Scholar
  10. 10.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), Part II, pp. 424–432 (2016)CrossRefGoogle Scholar
  11. 11.
    Espinoza, E., Martinez, G., Frerichs, J., Scheper, T.: Cell cluster segmentation based on global and local thresholding for in-situ microscopy. In: Proceedings of IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 542–545 (2006)Google Scholar
  12. 12.
    Essa, E., Xie, X., Errington, R.J., White, N.S.: A multi-stage random forest classifier for phase contrast cell segmentation. In: Proceedings of International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3865–3868 (2015)Google Scholar
  13. 13.
    Hilsenbeck, O., et al.: FastER: a user-friendly tool for ultrafast and robust cell segmentation in large-scale microscopy. Bioinformatics 33(13), 2020–2028 (2017)CrossRefGoogle Scholar
  14. 14.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of ACM International Conference on Multimedia (MM), pp. 675–678 (2014)Google Scholar
  15. 15.
    Klemm, S., Scherzinger, A., Drees, D., Jiang, X.: Barista - a graphical tool for designing and training deep neural networks. CoRR abs/1802.04626 (2018).
  16. 16.
    Lammel, U., et al.: The drosophila FHOD1-like formin Knittrig acts through Rok to promote stress fiber formation and directed macrophage migration during the cellular immune response. Development 14(1), 1366–1380 (2014)CrossRefGoogle Scholar
  17. 17.
    Lee, D.H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: ICML Workshop: Challenges in Representation Learning (WREPL) (2013)Google Scholar
  18. 18.
    Marcuzzo, M., Quelhas, P., Campilho, A., Mendonça, A.M., Campilho, A.: Automated arabidopsis plant root cell segmentation based on SVM classification and region merging. Comput. Biol. Med. 39(9), 785–793 (2009)CrossRefGoogle Scholar
  19. 19.
    Milletari, F., Navab, N., Ahmadi, S.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: International Conference on 3D Vision (3DV), pp. 565–571 (2016)Google Scholar
  20. 20.
    Pastor-Pellicer, J., Zamora-Martínez, F., Boquera, S.E., Bleda, M.J.C.: F-measure as the error function to train neural networks. In: Proceedings of International Work-Conference on Artificial Neural Networks (IWANN), Part I, pp. 376–384 (2013)CrossRefGoogle Scholar
  21. 21.
    Pinidiyaarachchi, A., Wählby, C.: Seeded watersheds for combined segmentation and tracking of cells. In: Roli, F., Vitulano, S. (eds.) Proceedings of Image Analysis and Processing (ICIAP), pp. 336–343 (2005)CrossRefGoogle Scholar
  22. 22.
    Raza, S., Cheung, L., Epstein, D.B.A., Pelengaris, S., Khan, M., Rajpoot, N.M.: Mimo-net: a multi-input multi-output convolutional neural network for cell segmentation in fluorescence microscopy images. In: Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), pp. 337–340 (2017)Google Scholar
  23. 23.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), Part III, pp. 234–241 (2015)Google Scholar
  24. 24.
    Rüder, M., Nagel, B.M., Bogdan, S.: Analysis of cell shape and cell migration of Drosophila macrophages in vivo. In: Gautreau, A. (ed.) Cell Migration. MMB, vol. 1749, pp. 227–238. Springer, New York (2018). Scholar
  25. 25.
    Sadanandan, S.K., Ranefall, P., Wählby, C.: Feature augmented deep neural networks for segmentation of cells. In: Proceedings of European Conference on Computer Vision (ECCV) Workshops, Part I, pp. 231–243 (2016)Google Scholar
  26. 26.
    Sander, M., Squarr, A.J., Risse, B., Jiang, X., Bogdan, S.: Drosophila pupal macrophages - a versatile tool for combined ex vivo and in vivo imaging of actin dynamics at high resolution. Eur. J. Cell Biol. 92(10–11), 349–354 (2013)CrossRefGoogle Scholar
  27. 27.
    Scherzinger, A., Klemm, S., Berh, D., Jiang, X.: CNN-based background subtraction for long-term in-vial FIM imaging. In: Proceedings of International Conference on Computer Analysis of Images and Patterns (CAIP), Part I, pp. 359–371 (2017)CrossRefGoogle Scholar
  28. 28.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  29. 29.
    Valen, D.A.V., et al.: Deep learning automates the quantitative analysis of individual cells in live-cell imaging experiments. PLoS Comput. Biol. 12(11), e1005177 (2016)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Aaron Scherzinger
    • 1
  • Philipp Hugenroth
    • 1
  • Marike Rüder
    • 2
  • Sven Bogdan
    • 2
  • Xiaoyi Jiang
    • 1
    Email author
  1. 1.Faculty of Mathematics and Computer Science, University of MünsterMünsterGermany
  2. 2.Institute for Physiology and Pathophysiology, Department of Molecular Cell PhysiologyPhilipps-University MarburgMarburgGermany

Personalised recommendations